© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62633
    Prev
    Next
    INDEX
    Explanations

    file identifiers and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     décisions
    -0.67
     Decide
    -0.66
    Decide
    -0.65
     religioso
    -0.65
     задержа
    -0.65
    exe
    -0.63
     mux
    -0.63
    Rationale
    -0.63
     junior
    -0.63
     Gott
    -0.63
    POSITIVE LOGITS
    ixante
    0.72
     JO
    0.72
    Omar
    0.70
    گن
    0.70
     aconteceu
    0.70
     devait
    0.69
     chemicals
    0.68
    ranger
    0.68
    ceptive
    0.67
     apareció
    0.67
    Activations Density 0.083%

    No Known Activations